Core Concepts

Learn the key concepts used in VJSP

Model Name	Describe
Foundational Models	Large AI models trained on massive datasets that serve as the foundation for AI applications, providing core capabilities in language understanding and generation.
Prompt Engineering	The art and science of crafting effective inputs for AI models to elicit desired outputs. Use the enhancement button to optimize your prompts.
Modes	In VJSP, you can choose Architect mode to plan and design software, Code mode to write and refactor code, Ask mode to understand a codebase, Debug mode to fix software issues, and Orchestrator mode to coordinate tasks across multiple modes.
Codebase Indexing	The codebase indexing feature leverages AI embedding technology to enable semantic code search across the entire project.
MCP (Model Context Protocol)	A standardized protocol for managing context and communication between AI models and external systems, enabling seamless integration with tools, databases, and services.